Proceedings of the 3rd International Conference on Vision, Image and Signal Processing最新文献_第2页

Automatic Compression Ratio Allocation for Pruning Convolutional Neural Networks 卷积神经网络的自动压缩比分配

Proceedings of the 3rd International Conference on Vision, Image and Signal Processing Pub Date : 2019-08-26 DOI: 10.1145/3387168.3387184

Yunfeng Liu, Huihui Kong, Peihua Yu

{"title":"Automatic Compression Ratio Allocation for Pruning Convolutional Neural Networks","authors":"Yunfeng Liu, Huihui Kong, Peihua Yu","doi":"10.1145/3387168.3387184","DOIUrl":"https://doi.org/10.1145/3387168.3387184","url":null,"abstract":"Convolutional neural networks (CNNs) have demonstrated significant performance improvement in many application scenarios. However, the high computational complexity and model size have limited its application on the mobile and embedded devices. Various approaches have been proposed to compress CNNs. Filter pruning is widely considered as a promising solution, which can significantly speed up the inference and reduce memory consumption. To this end, most approaches tend to prune filters by manually allocating compression ratio, which highly relies on individual expertise and not friendly to non-professional users. In this paper, we propose an Automatic Compression Ratio Allocation (ACRA) scheme based on binary search algorithm to prune convolutional neural networks. Specifically, ACRA provides two strategies for allocating compression ratio automatically. First, uniform pruning strategy allocates the same compression ratio to each layer, which is obtained by binary search based on target FLOPs reduction of the whole networks. Second, sensitivity-based pruning strategy allocates appropriate compression ratio to each layer based on the sensitivity to accuracy. Experimental results from VGG11 and VGG-16, demonstrate that our scheme can reduce FLOPs significantly while maintaining a high accuracy level. Specifically, for the VGG16 on CIFAR-10 dataset, we reduce 29.18% FLOPs with only 1.24% accuracy decrease.","PeriodicalId":346739,"journal":{"name":"Proceedings of the 3rd International Conference on Vision, Image and Signal Processing","volume":"18 8","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120846733","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

An Approach Based on Fuzzy Logic, to Improve Quality Management on Research and Development Centres 基于模糊逻辑的研发中心质量管理改进方法

Proceedings of the 3rd International Conference on Vision, Image and Signal Processing Pub Date : 2019-08-26 DOI: 10.1145/3387168.3387232

Ricardo Santos, A. Abreu, J. Calado, V. Anes

引用次数: 2

Facial Expression Classification and Recognition Based on Improved Hybrid CNN-ELM Model 基于改进CNN-ELM混合模型的面部表情分类与识别

Proceedings of the 3rd International Conference on Vision, Image and Signal Processing Pub Date : 2019-08-26 DOI: 10.1145/3387168.3387182

Chang-Xin Wang, Fei-Tian Li, Xiaoyu Tang, Zuo Huang

引用次数: 0

3D Position Estimation of Endoscopic Surgical Instruments: A Comparison of Monocular and Binocular Algorithms Using on IR Markers 内窥镜手术器械的三维位置估计:单眼和双目红外标记算法的比较

Proceedings of the 3rd International Conference on Vision, Image and Signal Processing Pub Date : 2019-08-26 DOI: 10.1145/3387168.3387173

Pin-Hsun Chiu, D. Shen

{"title":"3D Position Estimation of Endoscopic Surgical Instruments: A Comparison of Monocular and Binocular Algorithms Using on IR Markers","authors":"Pin-Hsun Chiu, D. Shen","doi":"10.1145/3387168.3387173","DOIUrl":"https://doi.org/10.1145/3387168.3387173","url":null,"abstract":"This paper develops a 3D positioning system for endoscopic surgical instruments Combining 3D virtual and augmented Reality, presents a wealth of opportunities in the field of medical science, especially where complex microsurgery is concerned. This paper develops 3D position reference coordinates between endoscopy instruments and the miniaturized camera required to perform surgery. The camera and markers used are infrared based which avoids confounding factors such as background colorings and light refractions. A comparison is made of monocular PnP and two different stereoscopic 3D attitude estimation methods for binocular stereo vision. It was found that monocular PnP is more accurate in stereo vision is generally more accurate. Inclusion of 3D modeling software. Unity to map the visualized surgical instrument, doctor could conceivably gain improved understanding of the surgical environment. This research is an initial effort at establishing Taiwan's MIS 3D attitude estimation processes, and it is hoped that it will eventually compete with the global brands such as NDI.","PeriodicalId":346739,"journal":{"name":"Proceedings of the 3rd International Conference on Vision, Image and Signal Processing","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128254502","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Machine Learning Distracted Driving Prediction Model 机器学习分心驾驶预测模型

Proceedings of the 3rd International Conference on Vision, Image and Signal Processing Pub Date : 2019-08-26 DOI: 10.1145/3387168.3387198

S. Ahangari, M. Jeihani, A. Dehzangi

{"title":"A Machine Learning Distracted Driving Prediction Model","authors":"S. Ahangari, M. Jeihani, A. Dehzangi","doi":"10.1145/3387168.3387198","DOIUrl":"https://doi.org/10.1145/3387168.3387198","url":null,"abstract":"Distracted driving is known to be one of the core contributors to crashes in the U.S., accounting for about 40% of all crashes. Drivers' situational awareness, decision-making, and driving performance are impaired due to temporarily diverting their attention from the primary task of driving to other tasks not related to driving. Detecting driver distraction would help in adapting the most effective countermeasures. To find the best strategies to overcome this problem, we developed a Bayesian Network (BN) distracted driving prediction model using a driving simulator. In this study, we use a Bayesian Network classifier as a powerful machine learning algorithm on our trained data (80%) and tested (20%) with the data collected from a driving simulator, in which the 92 participants drove six scenarios of hand-held calling, hands-free calling, texting, voice command, clothing, and eating/drinking on four different road classes (rural collector, freeway, urban arterial, and local road in a school zone). Various driving performances such as speed, acceleration, throttle, lane changing, brake, collision, and offset from the lane center were investigated. Here we investigated different optimization models to build the best BN in which a Genetic Search Algorithm obtained the best performance. As a result, we achieved a 67.8% prediction accuracy using our model to predict driver distraction. We also achieved 62.6% true positive rate, which demonstrates the ability of our model to correctly predict distractions.","PeriodicalId":346739,"journal":{"name":"Proceedings of the 3rd International Conference on Vision, Image and Signal Processing","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126761542","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 11

Traffic Impedance Estimation Driven by Trajectories for Urban Roads 基于轨迹的城市道路交通阻抗估计

Proceedings of the 3rd International Conference on Vision, Image and Signal Processing Pub Date : 2019-08-26 DOI: 10.1145/3387168.3387209

Li Liang, Yongjian Yang, Hengzhi Wang, Liping Huang, Xingliang Zhang

{"title":"Traffic Impedance Estimation Driven by Trajectories for Urban Roads","authors":"Li Liang, Yongjian Yang, Hengzhi Wang, Liping Huang, Xingliang Zhang","doi":"10.1145/3387168.3387209","DOIUrl":"https://doi.org/10.1145/3387168.3387209","url":null,"abstract":"Traffic impedance has attracted massive attention. The accurate estimation for the travel time along a specific road segment is of great significance for public traffic assignment and personal travel planning. The representative impedance function requires the traffic flow on corresponding road segments as inputs. However, traffic monitoring systems available cover quite limited number of roads in urban environment, which making it impossible for unmonitored roads' impedance estimation. Fortunately, the ubiquitous trajectories generated by the probe vehicles on the urban roads just make up for this defect, thus the main challenge is how to utilize trajectories to estimate road traffic impedance. In this paper, we propose a speed-based impedance function (SIF) for urban roads with consideration of road intersection. We divide the travel time of a road into the free flow driving part and the road intersection queuing part. Inspired by the impedance function of BPR (Bureau of Public Roads), we apply its simple deformation to the driving part. For the queuing part, we propose a novel simple speed-based computing model. Evaluation on several urban roads with real trajectory data demonstrates the effectiveness of our proposed method.","PeriodicalId":346739,"journal":{"name":"Proceedings of the 3rd International Conference on Vision, Image and Signal Processing","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123829062","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

Automated Classification of Malaria Parasite Stages Using Convolutional Neural Network-Classification of Life-cycle Stages of Malaria Parasites 基于卷积神经网络的疟疾寄生虫生命周期阶段自动分类

Proceedings of the 3rd International Conference on Vision, Image and Signal Processing Pub Date : 2019-08-26 DOI: 10.1145/3387168.3387185

Md. Khayrul Bashar

{"title":"Automated Classification of Malaria Parasite Stages Using Convolutional Neural Network-Classification of Life-cycle Stages of Malaria Parasites","authors":"Md. Khayrul Bashar","doi":"10.1145/3387168.3387185","DOIUrl":"https://doi.org/10.1145/3387168.3387185","url":null,"abstract":"Malarial is a mosquito born deadly disease that quickly grows from person to person because of the infectious mosquito bite. Knowing accurately the life-cycle stages of malaria parasite is critical for accurate drag selection for early recovery. When the infected mosquito bites the host, cell morphology and appearance greatly change through four major developmental stages namely ring, trophozoite, schizont, and gametocytes in the host's liver and later in the red blood cells (RBCs). Microscopy images carry the signatures of the above changes. However, widely used image analysis based computational techniques require expertise in analyzing morphological, texture, and color variations in the images. In this study, we investigate the strength of convolutional neural network (CNN) towards effective classification of malaria parasite stages. We design a customized CNN model to discriminate five classes including the control and four malaria parasite stages as mentioned above. With an imbalanced dataset having 46,973 single-cell thin blood smear images, the proposed method achieves 97.7% average accuracy, which is about 8~10% higher when compared with a pre-trained CNN model and a widely used hand crafted feature based model using support vector machine (SVM) classifier.","PeriodicalId":346739,"journal":{"name":"Proceedings of the 3rd International Conference on Vision, Image and Signal Processing","volume":"74 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122561831","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Partial Relay Selection Based Energy Harvesting Cooperative System with TAS and Outdated Channel State Information 基于TAS和过时信道状态信息的部分中继选择能量收集协同系统

Proceedings of the 3rd International Conference on Vision, Image and Signal Processing Pub Date : 2019-08-26 DOI: 10.1145/3387168.3387233

K. Odeyemi, P. Owolawi

{"title":"Partial Relay Selection Based Energy Harvesting Cooperative System with TAS and Outdated Channel State Information","authors":"K. Odeyemi, P. Owolawi","doi":"10.1145/3387168.3387233","DOIUrl":"https://doi.org/10.1145/3387168.3387233","url":null,"abstract":"In this paper, the performance of an energy harvesting based partial relay selection (PRS) cooperative system with transmit antenna selection (TAS) and outdated channel state information (CSI) is presented. The system dual-hops links are assumed to follow Rayleigh distribution and the relay selection is based on outdated CSI of the first link. The amplified-and-forward (AF) relay nodes are equipped with a single receive antenna and multiple transmit antenna while the destination utilized multiple receive antenna. Consequently, the cooperative system then employs the TAS technique at the relay nodes and maximum ratio combining (MRC) scheme is used at the destination. Based on this, the analytical closed-form expressions for the outage probability and throughput in delay-limited transmission mode are derived. The results demonstrated that the energy harvesting time, relay distance, channel correlation coefficient, the number of relay transmit antennas and destination received antenna have significant impact on the system performance. The accuracy of the derived expressions is validated by Monte-carol simulation.","PeriodicalId":346739,"journal":{"name":"Proceedings of the 3rd International Conference on Vision, Image and Signal Processing","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132580564","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Illumination Compensation And Image Denoising for Low-Light Images Based on Deep Learning 基于深度学习的微光图像光照补偿与去噪

Proceedings of the 3rd International Conference on Vision, Image and Signal Processing Pub Date : 2019-08-26 DOI: 10.1145/3387168.3387243

Hong Li, Yao Xia, Guoqing Yang, Pan Lv

引用次数: 1

Shared Word Embedding Space Modeling Method Based on Orthogonal Projection 基于正交投影的共享词嵌入空间建模方法

Proceedings of the 3rd International Conference on Vision, Image and Signal Processing Pub Date : 2019-08-26 DOI: 10.1145/3387168.3387250

Gang Liu, Kai Wang, Wangyang Liu, Yang Cao, Guang Li

引用次数: 0